Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. 'Linter' and 'flags' imply a non-mutating analysis pass, but nothing states the return shape, whether findings are advisory or blocking, or how the text under audit is supplied. For an audit tool with a completely empty input schema, this is a significant disclosure gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single tight sentence with the core concept front-loaded and the three detection categories listed after the colon. It wastes no words, though the extreme compression leaves the input/output contract unaddressed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description presents a tool that audits text, yet the input schema declares no properties and there is no output schema. Nothing explains how the target text reaches the tool or what comes back, leaving the call contract materially under-specified for an audit operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so per the rubric the baseline is 4. There is no parameter surface for the description to explain, and nothing it says misrepresents the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('linter for AI output') and enumerates exactly what it detects: unsupported certifications, fabricated authority, uncited statistics. That is far more concrete than a tautology. It does not, however, differentiate itself from plausible siblings like verify_text or attest_quality, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'for AI output' implies a domain but gives no explicit when-to-use or when-not-to-use guidance, and no alternative is named despite several overlapping siblings (verify_text, attest_quality, screen_message). The agent must infer the boundary entirely on its own.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.